Berlin researchers develop a robot that can learn to navigate through its environment guided by external stimuli
Researchers of Freie Universität Berlin, of the Bernstein Fokus Neuronal Basis of Learning, and of the Bernstein Center Berlin and have developed a robot that perceives environmental stimuli and learns to react to them. The scientists used the relatively simple nervous system of the honeybee as a model for its working principles. To this end, they installed a camera on a small robotic vehicle and connected it to a computer. The computer program replicated in a simplified way the sensorimotor network of the insect brain. The input data came from the camera that—akin to an eye—received and projected visual information. The neural network, in turn, operated the motors of the robot wheels—and could thus control its motion direction.
The outstanding feature of this artifical mini brain is its ability to learn by simple principles. “The network-controlled robot is able to link certain external stimuli with behavioral rules,” says Professor Martin Paul Nawrot, head of the research team and professor of neuroscience at Freie Universität Berlin. “Much like honeybees learn to associate certain flower colors with tasty nectar, the robot learns to approach certain colored objects and to avoid others.”
In the learning experiment, the scientists located the network-controlled robot in the center of a small arena. Red and blue objects were installed on the walls. Once the robot’s camera focused on an object with the desired color—red, for instance—, the scientists triggered a light flash. This signal activated a so-called reward sensor nerve cell in the artificial network. The simultaneous processing of red color and the reward now led to specific changes in those parts of the network, which exercised control over the robot wheels. As a consequence, when the robot “saw” another red object, it started to move toward it. Blue items, in contrast, made it move backwards. “Just within seconds, the robot accomplishes the task to find an object in the desired color and to approach it,” explains Nawrot. “Only a single learning trial is needed, similar to experimental observations in honeybees.”
The current study was carried out at Freie Universität Berlin within an interdisciplinary collaboration between the research groups “Neuroinformatics” (Institute of Biology) led by Professor Martin Paul Nawrot and “Intelligent Systems and Robotics” (Institute of Computer Science) led by Professor Raúl Rojas. The scientists are now planning to expand their neural network by supplementing more learning principles. Thus, the mini brain will become even more powerful—and the robot more autonomous.
The Latest on: Robots with Insect Brains
[google_news title=”” keyword=”Robots with Insect Brains” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robots with Insect Brains
- Ruling: Iowa state auditor must provide more evidence to justify withholding emailson April 26, 2024 at 5:45 pm
The state auditor's office must do more to justify its decision to withhold from public release emails between his office and two journalists, the Iowa Supreme Court ruled.
- Reuters Videoon April 26, 2024 at 5:00 pm
Reuters, the news and media division of Thomson Reuters, is the world’s largest multimedia news provider, reaching billions of people worldwide every day. Reuters provides business, financial, ...
- Robots cannot outrun animals, but they're evolving fasteron April 26, 2024 at 11:30 am
Despite these efforts, today's robots still cannot match the natural abilities of many animals in terms of endurance ...
- Iowa universities balance retention with lawmaker concerns as tenure numbers slideon April 26, 2024 at 7:30 am
All three of the public universities have seen non-tenure-track numbers swell over the years, but UI has a much higher count in that category because of its “clinical” faculty who work in the UI ...
- Waterloo school board split on joining risk pool for utility serviceson April 24, 2024 at 7:00 am
The Board of Education Monday approved participation in a program that could cost Waterloo Community Schools more than what is required for utilities.
- 2D transistors can mimic a locust's brain to avoid collision— super-efficient tech could lower the energy costs of tomorrow's AIon April 22, 2024 at 10:01 am
IIT Bombay and King's College researchers worked together to create a 2D transistor in a research project studying advancements in AI machines.
- Insect flight is powered by an extraordinary structureon April 19, 2024 at 1:00 am
Researchers at the California Institute of Technology have delved into this question, revealing the complex mechanics behind insect flight ...
- Watch out, Boston Dynamics! Mentee Robotics unveils ‘AI-first’ roboton April 17, 2024 at 4:45 pm
While still a prototype, Menteebot has been designed to target household and warehouse applications with AI technologies.
- Capitol Notebook: Bill to prohibit firearms tracking headed to Iowa Gov. Reynolds’ deskon April 17, 2024 at 8:00 am
Financial institutions operating in the state would be prohibited from using a merchant code for credit card transactions at gun retailers meant to detect suspicious firearms and ammunition sales ...
- AI Scientists Create Humanoid Robot That 'Thinks' Its Way Through Taskson April 17, 2024 at 5:29 am
The MenteeBot prototype responds to voice commands and can pick up and carry a range of objects to complete household tasks using real-time 'cognitive maps.' ...
via Bing News